Most recent
-
Explainable AI
Machine learning models are not black-boxes; these models can easily be interpreted using tools like SHAP, LIME and Anchor. These tools can facilitate the understanding of the model and the business problem. We can used these tools to build better models and communicate how predictions are generated. This article demonstrates their use in a mortality model. -
Insights Into Life PBR Modeling Practices
Oliver Wyman recently completed its 2020 Life PBR Emerging Practices survey, with results providing a broad industry perspective on implementation impacts, strategy, assumptions and challenges. This article provides further insights into the trends and drivers observed around planned future refinements to PBR models. -
The Importance of Centralization of Actuarial Modeling Functions, Part 4 - DevOps and Automated Model Governance
This article describes how to externalize code of Moody's Axis platform to Visual Studio, so that all the actuarial calculation code run through corporate DevOps pipeline. This article gives specific examples of the author has used in his job to accomplish automated model governance. -
Five Surprising Benefits of Actuarial Model Conversion
Actuaries understand the technical benefits of converting their models to a modern actuarial system, such as new capabilities and upgraded technology. This article highlights additional, non-technical benefits that also come with model conversion. These benefits include advancements in attitudes and capacities among the team and across the company. -
Communicating Actuarial Model Results
Listen now as April Shen, FSA, CFA, interviews Eric Schwartz, FSA, MAAA, on communicating actuarial model results. In this podcast, Eric discusses key questions and strategies actuaries should think about when they communicate model results to various stakeholders. -
Julia for Actuaries
Feature article that supports the statement that actuaries who are competent coders will differentiate both themselves and the companies they work for. Coding ability will be useful no matter what tools are utilized every day and all of those tools and communities contribute to moving actuarial processes out of the “Spreadsheet Age.” -
Model Validation Under LDTI
Listen now as April Shen, FSA, MAAA interviews Jennifer Caplin, FSA, MAAA on the components, challenges and project management for model validation under LDTI. -
Undeniable Synergy - A Discussion on the Chief Modeling Officer Role with Van Beach
"Given today’s environment, the trajectory of modeling technologies and applications, and the mission-critical nature of modeling within insurance organizations, the time has come for the chief modeling officer. " What's the role description for a chief modeling officer? What is the organizational structure and institutional benefits for this role? Listen now as April Shen, FSA, MAAA interviews Van Beach, FSA, MAAA on the role of Chief Modeling Officer in insurance companies. -
Principal Component Analysis Using R
Principal component analysis is an unsupervised linear transformation mainly used for dimension reduction. Determine key numerical variables with maximum variances in a dataset, identify the correlation and removal of redundant variables are the key aspects of this exploratory data analysis. -
Data Warehouse, Data Lake or Data Swamp? Actuarial Modeling in the Big Data Era with Tom Peplow
Listen now as April Shen, FSA, CFA interviews Tom Peplow (Principal, Director of Product Development - LTS) on the interaction between actuarial modeling and big data. In this episode, Tom discusses the basic concept on data warehouse, tools and resources actuaries can use to learn more.
Welcome to our medium.
Dive into insightful content. Gain practical knowledge. Explore the latest research and key information for future use. Discover the Emerging Topics Community, an online forum that focuses on three main topic areas–Modeling, Predictive Analytics and Futurism, and Technology.